| User | anbG34 |
| Upload Date | May 19 2025 11:40 AM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.5 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,3 |
| Motherboard | J318AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.70 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
911
169.4 IPS |
|
|
Image Classification (HP)
|
100% |
1274
237.0 IPS |
|
|
Image Classification (Q)
|
96% |
151
28.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
338
5.48 IPS |
|
|
Image Segmentation (HP)
|
100% |
355
5.76 IPS |
|
|
Image Segmentation (Q)
|
99% |
223
3.62 IPS |
|
|
Pose Estimation (SP)
|
100% |
2816
3.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
4042
4.72 IPS |
|
|
Pose Estimation (Q)
|
96% |
1884
2.21 IPS |
|
|
Object Detection (SP)
|
100% |
892
70.8 IPS |
|
|
Object Detection (HP)
|
100% |
1199
95.1 IPS |
|
|
Object Detection (Q)
|
92% |
179
14.3 IPS |
|
|
Face Detection (SP)
|
100% |
3577
42.5 IPS |
|
|
Face Detection (HP)
|
100% |
4109
48.8 IPS |
|
|
Face Detection (Q)
|
100% |
293
3.48 IPS |
|
|
Depth Estimation (SP)
|
100% |
2933
22.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
4226
32.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
535
4.18 IPS |
|
|
Style Transfer (SP)
|
100% |
7944
10.2 IPS |
|
|
Style Transfer (HP)
|
100% |
9894
12.7 IPS |
|
|
Style Transfer (Q)
|
96% |
3024
3.90 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1398
51.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1839
67.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
397
14.7 IPS |
|
|
Text Classification (SP)
|
100% |
216
288.7 IPS |
|
|
Text Classification (HP)
|
100% |
260
347.4 IPS |
|
|
Text Classification (Q)
|
93% |
275
369.0 IPS |
|
|
Machine Translation (SP)
|
100% |
509
8.76 IPS |
|
|
Machine Translation (HP)
|
100% |
477
8.21 IPS |
|
|
Machine Translation (Q)
|
98% |
465
8.04 IPS |